{
  "id": 6084,
  "url": "https://arxiv.org/abs/2604.08963v2",
  "title": "Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems",
  "summary": "While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely, evaluating their ethical robustness requires first isolating their foundational mechanics. In this work, we conduct a baseline empirical study investigating how basic MAS topologies and feedback loops influence prejudice. Contrary to the assumption that multi-agent col",
  "authors": "Keyu Li, Jin Gao, Dequan Wang",
  "category": "research",
  "topics": "bias-fairness,agents-autonomy,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-10T05:06:38.000Z",
  "fetched_at": "2026-07-14T16:32:15.634Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6084",
  "original_url": "https://arxiv.org/abs/2604.08963v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}